arXiv Machine Learning August 28, 2026 By Zijie Cheng, Xiang Li, Yang Peng, Zhihua Zhang

A Finite Sample Analysis for Quantile Temporal Difference Learning in Distributional Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2608. 27313v1 Announce Type: cross Abstract: We establish a global finite-sample guarantee for synchronous quantile temporal-difference learning (QTD) in tabular distributional reinforcement learning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

reinforcement-learning

Hugging Face Trending Papers

Aug 27

A Finite Sample Analysis for Quantile Temporal Difference Learning in Distributional Reinforcement Learning

We establish a global finite-sample guarantee for synchronous quantile temporal-difference learning (QTD) in tabular distributional reinforcement learning. The proof separates two stability mechanisms.

reinforcement-learning

arXiv Machine Learning

Aug 14

Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning

arXiv:2608. 12973v1 Announce Type: cross Abstract: In this paper, we study how to perform statistical inference for quantile temporal difference learning (QTD) in distributional reinforcement learning.

By Zijie Cheng, Yang Peng, Zhihua Zhang

reinforcement-learning

arXiv AI

Jul 7

Sign-Separated Asymmetric Finite-Time Error Analysis of Q-Learning

arXiv:2605. 16103v2 Announce Type: replace Abstract: Q-learning is known to suffer from overestimation bias: because the Bellman update maximizes noisy or imperfect action-value estimates, positive errors can be selected and propagated, causing learned values to exceed the true optimal values.

By Donghwan Lee

reinforcement-learning safety

arXiv Machine Learning

Aug 4

Upper-Expectile Multi-Step Q-Learning for Off-Policy Reinforcement Learning

arXiv:2608. 02034v1 Announce Type: new Abstract: Multi-step returns accelerate reward propagation in off-policy reinforcement learning, but couple the evaluation of each decision to the suboptimal logged actions that follow it, inducing a pessimistic bias that grows with the horizon.

By Abdelghani Ghanem, Mounir Ghogho

reinforcement-learning robotics efficiency safety

arXiv Machine Learning

Jun 5

Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples

arXiv:2606. 05967v1 Announce Type: cross Abstract: In this paper, we study the finite-time behavior of the TD(0) temporal-difference method with linear function approximation (LFA).

By Ziad Kobeissi (L2S), \'Elo\"ise Berthier (U2IS)

arXiv Machine Learning

Jul 10

Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning

arXiv:2607. 08444v1 Announce Type: cross Abstract: In this paper, we study quantile-based distributional reinforcement learning from the perspective of statistical efficiency.

By Zijie Cheng, Yang Peng, Zhihua Zhang

reinforcement-learning

One email a morning, machine-written

Related stories

A Finite Sample Analysis for Quantile Temporal Difference Learning in Distributional Reinforcement Learning

Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning

Sign-Separated Asymmetric Finite-Time Error Analysis of Q-Learning

Upper-Expectile Multi-Step Q-Learning for Off-Policy Reinforcement Learning

Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples

Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning